Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99772
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delimiter
    -0.07
    евых
    -0.07
    -public
    -0.07
    tickets
    -0.07
    .so
    -0.06
    #c
    -0.06
     NOTICE
    -0.06
     معرفی
    -0.06
    counter
    -0.06
    Header
    -0.06
    POSITIVE LOGITS
     wedge
    0.07
     άλ
    0.07
    LOY
    0.06
    PD
    0.06
    .intent
    0.06
     Conversation
    0.06
    mlx
    0.06
    '>";↵
    0.06
    .Fire
    0.06
     organized
    0.06
    Activations Density 0.031%

    No Known Activations